Here we show the code to reproduce the analyses of: Risso and Pagnotta (2020). Per-sample standardization and asymmetric winsorization lead to accurate classification of RNA-seq expression profiles. In preparation.
This file belongs to the repository: https://github.com/drisso/awst_analysis.
The code is released with license GPL v3.0.
Install and load awst
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("drisso/awst")
The synthetic dataset
… We then created \(k=5\) groups of samples, each made of \(M=30\) replicate samples, randomly selected (with replacement) from the original set of 80. For each group, we randomly selected (without replacement) \(J=500\) genes, whose expression was altered according to the following multiplicative model. \[
\tilde{y}_j = y_j \cdot (0.001 + r_j), \quad j=1,\ldots,J,
\] where \(y_j\) denotes the observed expression of gene \(j\), \(\tilde{y}\) denotes the perturbed expression, and \(r_j\) is the realization of a Gamma random variable with shape parameter \(a=0.5\) and scale parameter \(s=1\).
#BiocManager::install("seqc") # uncomment if necessary
rm(list = ls())
set.seed(20200413)
library(seqc)
ddata <- get("ILM_aceview_gene_MAY")
ddata <- ddata[!is.na(ddata$EntrezID),]
ddata <- ddata[!ddata$IsERCC,]
feature_annotation <- data.frame(ddata[, 1:3], row.names = ddata$EntrezID)
dim(ddata <- as.matrix(ddata[, -c(1:4)])) #[1] 19701 384
sum(duplicated(feature_annotation$Symbol)) #[1] 0
sum(duplicated(feature_annotation$EntrezID)) #[1] 0
row.names(ddata) <- feature_annotation$EntrezID
dim(sample_annotation.df <- data.frame(row.names = colnames(ddata), sample = colnames(ddata))) #[1] 384 1
sample_annotation.df$lane <- substr(sample_annotation.df$sample, 6, 7)
sample_annotation.df$flow_cell <- substr(sample_annotation.df$sample, 17, 17)
sample_annotation.df$sample <- substr(sample_annotation.df$sample, 1, 3)
sample_annotation.df <- sample_annotation.df[grep("A", sample_annotation.df$sample),]
dim(ddata <- ddata[, rownames(sample_annotation.df)]) #[1] 19701 80
M <- 30
nnumbers <- c("01", "02", "03", "04", "05", "06", "07", "08", "09", paste(10:M))
tmp <- c(paste0("A", nnumbers), paste0("B", nnumbers), paste0("C", nnumbers),
paste0("D", nnumbers), paste0("E", nnumbers))
design.df <- data.frame(row.names = tmp, sample = tmp, original.sample = NA)
design.df$original.sample[1:M] <- sample(rownames(sample_annotation.df), M, replace = TRUE)
design.df$original.sample[(M+1):(2*M)] <- sample(rownames(sample_annotation.df), M, replace = TRUE)
design.df$original.sample[(2*M+1):(3*M)] <- sample(rownames(sample_annotation.df), M, replace = TRUE)
design.df$original.sample[(3*M+1):(4*M)] <- sample(rownames(sample_annotation.df), M, replace = TRUE)
design.df$original.sample[(4*M+1):(5*M)] <- sample(rownames(sample_annotation.df), M, replace = TRUE)
# table(design.df$original.sample)
k <- "A"
wwhich <- grep(k, design.df$sample)
synthetic_data <- ddata[, design.df$original.sample[wwhich]]
colnames(synthetic_data) <- design.df$sample[wwhich]
the_genes <- rownames(synthetic_data)
no_of_altered_genes <- 500
genes_to_alterate <- sample(the_genes, no_of_altered_genes, replace = FALSE)
the_genes <- the_genes[-which(the_genes %in% genes_to_alterate)]
for(jj in 1:M) {
tmp <- 0.001 + rgamma(length(genes_to_alterate), shape = 0.5, scale = 1)
synthetic_data[genes_to_alterate, jj] <- synthetic_data[genes_to_alterate, jj] * tmp
}
# k <- "B"
for(k in c("B", "C", "D", "E")) {
wwhich <- grep(k, design.df$sample)
tmp_data <- ddata[, design.df$original.sample[wwhich]]
colnames(tmp_data) <- design.df$sample[wwhich]
genes_to_alterate <- sample(the_genes, no_of_altered_genes, replace = FALSE)
the_genes <- the_genes[-which(the_genes %in% genes_to_alterate)]
for(jj in 1:M) {
tmp <- 0.001 + rgamma(length(genes_to_alterate), shape = 0.5, scale = 1)
tmp_data[genes_to_alterate, jj] <- tmp_data[genes_to_alterate, jj] * tmp
}
synthetic_data <- cbind(synthetic_data, tmp_data)
}
dim(ddata <- floor(synthetic_data)) #[1] 19701 150
annotation.df <- data.frame(samples = colnames(ddata), row.names = colnames(ddata))
annotation.df$sample <- substr(annotation.df$samples, 1, 1)
annotation.df$sample.col <- factor(annotation.df$sample)
levels(annotation.df$sample.col) <- clust.col <- c("gold", "red", "green2", "blue", "cyan")
names(clust.col) <- unique(annotation.df$sample)
save(ddata, annotation.df, feature_annotation, clust.col, file = "synthetic20200413.RData")
#tmp <- cbind(annotation.df, t(ddata))
#write.table(tmp, file = "synthetic20200413.tsv", sep = "\t", quote = FALSE, row.names = FALSE)
#write.table(feature_annotation, file = "synthetic20200413_features_annotation.tsv", sep = "\t", quote = FALSE, row.names = FALSE)
AWST procedure
hclust (Euclidean/Ward)
## user system elapsed
## 0.919 0.007 0.928

## null device
## 1
## null device
## 1
## cluster accuracy (eca): 0.9917
## cluster purity (ecp): 0.9914
## adjusted Rand's index (ari): 0.9832
## G index (geometric average of eca, ecp, and ari): 0.9887
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Hart 2013
Finding the active genes in deep RNA-seq gene expression studies
hclust (Euclidean/Ward)
## user system elapsed
## 0.609 0.000 0.608

## null device
## 1
## null device
## 1
## cluster accuracy (eca): 0.9122
## cluster purity (ecp): 0.8829
## adjusted Rand's index (ari): 0.6779
## G index (geometric average of eca, ecp, and ari): 0.8173
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.7377
## cluster purity (ecp): 0.9315
## adjusted Rand's index (ari): 0.6924
## G index (geometric average of eca, ecp, and ari): 0.7806
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Radovich (2018) procedure
The Integrated Genomic Landscape of Thymic Epithelial Tumors
hclust (Euclidean/Ward)
## user system elapsed
## 1.227 0.000 1.227

## null device
## 1
## cluster accuracy (eca): 0.6775
## cluster purity (ecp): 0.6563
## adjusted Rand's index (ari): 0.0848
## G index (geometric average of eca, ecp, and ari): 0.3354
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## cluster accuracy (eca): 0.6201
## cluster purity (ecp): 0.6072
## adjusted Rand's index (ari): 0.0347
## G index (geometric average of eca, ecp, and ari): 0.2355
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
TCGA (2015) procedure
Comprehensive, Integrative Genomic Analysis of Diffuse Lower-Grade Gliomas - Supplementary Appendix (see pages 23-24)
hclust (Euclidean/Ward)
## user system elapsed
## 3.701 0.044 3.750


## cluster accuracy (eca): 0.3872
## cluster purity (ecp): 0.8364
## adjusted Rand's index (ari): 0.0013
## G index (geometric average of eca, ecp, and ari): 0.0742
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.5595
## cluster purity (ecp): 0.6445
## adjusted Rand's index (ari): 0.1102
## G index (geometric average of eca, ecp, and ari): 0.3412
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 0.3872
## cluster purity (ecp): 0.8364
## adjusted Rand's index (ari): 0.0013
## G index (geometric average of eca, ecp, and ari): 0.0742
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
FPKM: Top 2500 features
## user system elapsed
## 0.136 0.008 0.145


## null device
## 1
## cluster accuracy (eca): 0.881
## cluster purity (ecp): 0.8299
## adjusted Rand's index (ari): 0.4637
## G index (geometric average of eca, ecp, and ari): 0.6973
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.7717
## cluster purity (ecp): 0.7711
## adjusted Rand's index (ari): 0.5204
## G index (geometric average of eca, ecp, and ari): 0.6765
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
FPKM: Top 5000 features


## null device
## 1
## cluster accuracy (eca): 0.3872
## cluster purity (ecp): 0.8364
## adjusted Rand's index (ari): 0.0013
## G index (geometric average of eca, ecp, and ari): 0.0742
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.6104
## cluster purity (ecp): 0.6294
## adjusted Rand's index (ari): 0.1812
## G index (geometric average of eca, ecp, and ari): 0.4114
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 0.7841
## cluster purity (ecp): 0.8917
## adjusted Rand's index (ari): 0.6188
## G index (geometric average of eca, ecp, and ari): 0.7564
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
VST (DESeq2): all features


## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”)
## Loading required package: ConsensusClusterPlus
## end fraction
## clustered
## clustered
## clustered
## clustered
## clustered
## clustered

## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default)
## end fraction
## clustered
## clustered
## clustered
## clustered
## clustered
## clustered

## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
rLog (DESeq2): all features


## null device
## 1
## cluster accuracy (eca): 0.9309
## cluster purity (ecp): 0.8527
## adjusted Rand's index (ari): 0.3833
## G index (geometric average of eca, ecp, and ari): 0.6726
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.8166
## cluster purity (ecp): 0.7942
## adjusted Rand's index (ari): 0.509
## G index (geometric average of eca, ecp, and ari): 0.6911
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 0.9625
## cluster purity (ecp): 0.954
## adjusted Rand's index (ari): 0.8968
## G index (geometric average of eca, ecp, and ari): 0.9373
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
rLog (DESeq2) 2,500 HVG

## null device
## 1
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)
Result of ConsensuClusterPlus with clusterAlg = “pam” and distance = “euclidean” (other parameters left to default) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Townes/deviance (scry)

## null device
## 1
## null device
## 1
## cluster accuracy (eca): 0.9865
## cluster purity (ecp): 0.9856
## adjusted Rand's index (ari): 0.9669
## G index (geometric average of eca, ecp, and ari): 0.9796
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)

## null device
## 1
## cluster accuracy (eca): 0.9665
## cluster purity (ecp): 0.9627
## adjusted Rand's index (ari): 0.9166
## G index (geometric average of eca, ecp, and ari): 0.9483
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Townes/deviance (scry) 2,500HVG


## cluster accuracy (eca): 0.9865
## cluster purity (ecp): 0.9856
## adjusted Rand's index (ari): 0.9669
## G index (geometric average of eca, ecp, and ari): 0.9796
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## cluster accuracy (eca): 1
## cluster purity (ecp): 1
## adjusted Rand's index (ari): 1
## G index (geometric average of eca, ecp, and ari): 1
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)

## cluster accuracy (eca): 0.971
## cluster purity (ecp): 0.9685
## adjusted Rand's index (ari): 0.933
## G index (geometric average of eca, ecp, and ari): 0.9573
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Townes/pearson (scry)


## null device
## 1
## cluster accuracy (eca): 0.928
## cluster purity (ecp): 0.9102
## adjusted Rand's index (ari): 0.7555
## G index (geometric average of eca, ecp, and ari): 0.861
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.9264
## cluster purity (ecp): 0.9208
## adjusted Rand's index (ari): 0.8227
## G index (geometric average of eca, ecp, and ari): 0.8886
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)

## null device
## 1
## cluster accuracy (eca): 0.9297
## cluster purity (ecp): 0.9172
## adjusted Rand's index (ari): 0.805
## G index (geometric average of eca, ecp, and ari): 0.8821
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Townes/pearson (scry) 2,500HVG


## cluster accuracy (eca): 0.9689
## cluster purity (ecp): 0.9625
## adjusted Rand's index (ari): 0.9011
## G index (geometric average of eca, ecp, and ari): 0.9437
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (default parameters)
Result of ConsensuClusterPlus with default setup
(innerLinkage=“average”, finalLinkage=“average”, distance=“pearson”) 
## null device
## 1
## cluster accuracy (eca): 0.9826
## cluster purity (ecp): 0.9809
## adjusted Rand's index (ari): 0.9513
## G index (geometric average of eca, ecp, and ari): 0.9715
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
ConsensusClusterPlus (PAM)

## null device
## 1
## cluster accuracy (eca): 0.9601
## cluster purity (ecp): 0.9534
## adjusted Rand's index (ari): 0.8845
## G index (geometric average of eca, ecp, and ari): 0.932
## no. of clusters in theoretical partition: 5
## no. of clusters in estimated partition: 5
Table of the experiments
| AWST |
HC |
0.9917 |
0.9914 |
0.9832 |
0.9887 |
0.2465 |
0.848 |
| AWST |
CCP1 |
1 |
1 |
1 |
1 |
NA |
NA |
| AWST |
CCP2 |
1 |
1 |
1 |
1 |
NA |
NA |
| Hart |
HC |
0.9122 |
0.8829 |
0.6779 |
0.8173 |
0.1832 |
0.58 |
| Hart |
CCP1 |
0.7377 |
0.9315 |
0.6924 |
0.7806 |
NA |
NA |
| Hart |
CCP2 |
1 |
1 |
1 |
1 |
NA |
NA |
| Radovich |
HC |
0.6775 |
0.6563 |
0.0848 |
0.3354 |
0.0449 |
1.135 |
| Radovich |
CCP1 |
1 |
1 |
1 |
1 |
NA |
NA |
| Radovich |
CCP2 |
0.6201 |
0.6072 |
0.0347 |
0.2355 |
NA |
NA |
| TCGA |
HC |
0.3872 |
0.8364 |
0.0013 |
0.0742 |
0.0345 |
3.335 |
| TCGA |
CCP1 |
0.5595 |
0.6445 |
0.1102 |
0.3412 |
NA |
NA |
| TCGA |
CCP2 |
0.3872 |
0.8364 |
0.0013 |
0.0742 |
NA |
NA |
| FPKM (2,500HVG) |
HC |
0.881 |
0.8299 |
0.4637 |
0.6973 |
0.178 |
0.134 |
| FPKM (2,500HVG) |
CCP1 |
0.7717 |
0.7711 |
0.5204 |
0.6765 |
NA |
NA |
| FPKM (2,500HVG) |
CCP2 |
1 |
1 |
1 |
1 |
NA |
NA |
| FPKM (5,000HVG) |
HC |
0.3872 |
0.8364 |
0.0013 |
0.0742 |
0.0864 |
NA |
| FPKM (5,000HVG) |
CCP1 |
0.6104 |
0.6294 |
0.1812 |
0.4114 |
NA |
NA |
| FPKM (5,000HVG) |
CCP2 |
0.7841 |
0.8917 |
0.6188 |
0.7564 |
NA |
NA |
| VST |
HC |
1 |
1 |
1 |
1 |
0.2504 |
3.068 |
| VST |
CCP1 |
1 |
1 |
1 |
1 |
NA |
NA |
| VST |
CCP2 |
1 |
1 |
1 |
1 |
NA |
NA |
| rLog |
HC |
0.9309 |
0.8527 |
0.3833 |
0.6726 |
0.1728 |
927.896 |
| rLog |
CCP1 |
0.8166 |
0.7942 |
0.509 |
0.6911 |
NA |
NA |
| rLog |
CCP2 |
0.9625 |
0.954 |
0.8968 |
0.9373 |
NA |
NA |
| rLog (2,500HVG) |
HC |
1 |
1 |
1 |
1 |
0.2533 |
NA |
| rLog (2,500HVG) |
CCP1 |
1 |
1 |
1 |
1 |
NA |
NA |
| rLog (2,500HVG) |
CCP2 |
1 |
1 |
1 |
1 |
NA |
NA |
| Townes/deviance |
HC |
0.9865 |
0.9856 |
0.9669 |
0.9796 |
0.158 |
0.216 |
| Townes/deviance |
CCP1 |
1 |
1 |
1 |
1 |
NA |
NA |
| Townes/deviance |
CCP2 |
0.9665 |
0.9627 |
0.9166 |
0.9483 |
NA |
NA |
| Townes/deviance (2,500HVG) |
HC |
0.9865 |
0.9856 |
0.9669 |
0.9796 |
0.191 |
NA |
| Townes/deviance (2,500HVG) |
CCP1 |
1 |
1 |
1 |
1 |
NA |
NA |
| Townes/deviance (2,500HVG) |
CCP2 |
0.971 |
0.9685 |
0.933 |
0.9573 |
NA |
NA |
| Townes/pearson |
HC |
0.928 |
0.9102 |
0.7555 |
0.861 |
0.085 |
0.048 |
| Townes/pearson |
CCP1 |
0.9264 |
0.9208 |
0.8227 |
0.8886 |
NA |
NA |
| Townes/perason |
CCP2 |
0.9297 |
0.9172 |
0.805 |
0.8821 |
NA |
NA |
| Townes/pearson (2,500HVG) |
HC |
0.9689 |
0.9625 |
0.9011 |
0.9437 |
0.1099 |
NA |
| Townes/pearson (2,500HVG) |
CCP1 |
0.9826 |
0.9809 |
0.9513 |
0.9715 |
NA |
NA |
| Townes/pearson (2,500HVG) |
CCP2 |
0.9601 |
0.9534 |
0.8845 |
0.932 |
NA |
NA |
HC) hirerachical clustering with Ward’s likage and Euclidean distance; CPP1) ConsensusClusterPlus with average innner and outer linkage, and Pearson’s correlation as distance; CCP2) ConsensusClusterPlus with PAM and Euclidean distance;
Average Silhouettes Width

## null device
## 1